# Together AI Prompt Leak: AI Coding Agent Exposed a Hugging Face Credential

> Source: <https://explainx.ai/blog/together-ai-prompt-leak-xorl-huggingface-coding-agent-november-2026?utm_source=rss&utm_medium=feed&utm_campaign=blog>
> Published: 2026-11-22 00:00:00+00:00

**Together AI disclosed on November 21, 2026 that an unauthorized party downloaded stored prompt samples after an AI coding agent exposed a Hugging Face credential in its public xorl GitHub repository.** The [official notice](https://www.together.ai/blog/security-event-prompt-leakage-for-requests-in-june-and-july-of-2026?ref=explainx) names **MiniMax M3**, **GLM-5.2**, and **Kimi K2.6** serverless traffic on **June 24, July 4, July 8, and July 14, 2026**, and says **five Dragos canary credentials** embedded in those prompts were tested by the intruder.

## TL;DR: what Together AI confirms

| Item | Together AI's statement | 
|---|---|
| Root cause | AI coding agent committed HF repo credential during xorl development | 
| Detection | Automated scanning found credential; commit reverted | 
| Intruder action | Downloaded stored prompt samples during exposure window | 
| Follow-on | Searched samples for other credentials; tested five Dragos canaries | 
| Data fate | Party understood to have deleted data; no further leak claimed | 
| Customer action | Enable ZDR; contact [security@together.ai](mailto:security@together.ai) | 
| Scope review | Ongoing; direct notice if sensitive data found | 

This sits in the same week as [Dragos canary research](https://explainx.ai/blog/dragos-hd-moore-two-million-canary-prompts-three-provider-breaches-zdr-ignored-ai-routers-2026) and [OpenRouter's MiniMax customer emails](https://explainx.ai/blog/openrouter-minimax-prompts-may-have-been-read-customer-email-november-2026). The mechanisms differ, but the lesson for builders is the same: **prompts and dev credentials are attack surface**.

## What is zero data retention on Together AI?

**Zero data retention (ZDR)** is a Together AI account setting that tells the platform not to retain prompt and completion text for training or logging beyond what operations require. Together AI now says **ZDR is the default for new accounts** after this incident.

ZDR governs **production inference paths**. It does **not** automatically cover **engineering datasets** copied into private Hugging Face repos for QA. If your compliance story depends on ZDR alone, map **every copy** of prompt text, including **eval harnesses** and **customer support exports**.

Our [OpenRouter ZDR explainer thread](https://explainx.ai/blog/openrouter-minimax-prompts-may-have-been-read-customer-email-november-2026) shows how **badges on a marketplace** can disappear while investigators work. Together AI is making the opposite move, defaulting new tenants to stricter retention, but **existing accounts** must still toggle settings per the November 21 notice.

## Why Together AI stored prompts at all

Together AI says the samples were collected **as part of routine software testing** and kept in a **private Hugging Face repository**. That is separate from live production routing, but it still held real user prompt text from serverless calls unless testing used synthetic data only. The company does not say how many distinct customers appear in the archive.

Teams that run [Together AI agent evals](https://explainx.ai/blog/together-ai-agent-evals-97-percent-coding-agents-november-2026) already treat prompts as durable artifacts. This incident shows **where those artifacts land matters** as much as inference-time ZDR flags.

## The xorl repository and the AI coding agent

Green key sealed inside a capsule beside a closed project folder

**xorl** is Together AI's public GitHub project tied to its open inference stack. During development, an **AI coding agent** committed a credential that unlocked the private Hugging Face repo. Together AI's scanning caught the mistake and maintainers reverted the commit, but **revert does not revoke a credential that was already copied**.

That pattern matches other 2026 supply-chain stories where **agents write secrets into repos**:

- [Microsoft Agent Framework PyPI typo stealer](https://explainx.ai/blog/microsoft-agent-framework-pypi-1-26-credential-stealer-november-2026) showed how automated installs can pull malicious packages.

Together AI's response includes **PR credential scanning** and **scoped or short-lived credentials**, which are table stakes for any org letting agents touch git.

## Dragos canaries in the downloaded prompts

Vault door with a key hanging beside staged prompt credentials

Together AI explicitly says the intruder tested **five canary credentials associated with a Dragos security experiment**. That aligns with Dragos CRO HD Moore's November 19 post on **two million canary-laced prompts**, which we summarized in the [Dragos canary article](https://explainx.ai/blog/dragos-hd-moore-two-million-canary-prompts-three-provider-breaches-zdr-ignored-ai-routers-2026).

Canary tokens are **fake AWS keys or URLs that should never be used unless a system was compromised**. When they fire, you know **someone read prompt text** or **a provider logged it**. Here, Together AI confirms **post-download credential hunting**, not just passive storage.

Builders running coding agents should **seed their own canaries** in staging prompts and **never paste production API keys** into model chats, as Dragos recommends.

## Models and dates builders should check

Together AI lists these **serverless models** in the stored sample set:

| Model | Provider relationship | 
|---|---|
| MiniMax M3 | Third-party model on Together serverless | 
| GLM-5.2 | Z.ai GLM family | 
| Kimi K2.6 | Moonshot Kimi line Together [partners on natively](https://explainx.ai/blog/together-ai-agent-evals-97-percent-coding-agents-november-2026) | 

Dates named in the notice: **June 24, July 4, July 8, July 14, 2026**. If your team routed **customer support logs, code, or credentials** through those models on Together serverless on those days, **assume the text could be in the downloaded archive** until Together AI tells you otherwise.

This is **not** the same incident as OpenRouter's **MiniMax reseller forwarding** warning, which covers **July–October live traffic** on a router marketplace. Read both notices if you use **multiple hops**.

## Investigation and customer notification

Together AI says it engaged an **external forensic firm** and **law enforcement**. It reports **no evidence of additional prompt leakage** beyond this Hugging Face archive path, but **content review is ongoing** for personal or customer-sensitive data.

If you need a direct answer for compliance, **[security@together.ai](mailto:security@together.ai)** is the channel named in the post. Document **which workspaces** used serverless on the listed models in June–July 2026.

## Policy changes Together AI announced

The notice lists four concrete controls:

1. **Scoped or short-lived credentials** , plus keyless access where supported.
2. **Credential checks on all pull requests** .
3. **ZDR default for new accounts** .
4. **Updated development policies for AI coding agents** .

Default **zero data retention** helps **forward-looking** privacy, but it **does not retroactively protect** text already stored in a test Hugging Face dataset. Customers must **opt in explicitly** in settings for existing accounts, per the post.

## How to protect yourself

API key beside an open pocket with leaked credential drops

### For inference customers

- Turn on **ZDR** in Together AI settings before sending**PII, source code, or secrets** .
- **Rotate keys** that ever appeared in prompts during the named window.
- Prefer **direct enterprise endpoints** when contracts allow, as[Near AI's TEE breach post](https://explainx.ai/blog/near-ai-cloud-inference-breach-tee-november-2026) and Dragos both stress for sensitive workloads.
- Compare your stack to [Together prefix-cache guidance](https://explainx.ai/blog/together-ai-ollama-prefix-cache-long-horizon-agents-2026) only after**data-handling** choices are settled.

### For teams using AI coding agents on public repos

- Block commits that contain **HF tokens, AWS keys, or inference API keys** ; use**pre-commit and CI secret scanners** .
- Never give agents **production credentials** ; use**ephemeral tokens** per session.
- Split **evaluation datasets** into**synthetic-only** repos when possible.

For agent-specific guardrails in CI, see [Cognition's Corridor acquisition](https://explainx.ai/blog/cognition-acquires-corridor-devin-security-ex-cisa-founders-stamos-agent-written-code-guardrails-2026) and [AgentBeam's write-up of this incident](https://agentbeam.com/blog/together-ai-prompt-leak-coding-agent-xorl-huggingface-november-2026?ref=explainx) on stopping dangerous agent actions before they leak secrets.

## Context: why November 2026 feels like prompt-leak month

Three threads converged in one week:

| Date | Event | 
|---|---|
| Nov 19 | Dragos publishes canary study; three unnamed provider breaches | 
| Nov 21 AM | OpenRouter emails customers about MiniMax routes | 
| Nov 21 PM | Together AI publishes xorl / Hugging Face notice | 

Congressional concern about **AI-assisted patch cycles** during outages appears in [November outage reporting](https://explainx.ai/blog/ai-vulnerability-patch-rush-outages-warner-congress-november-2026). Prompt leaks are a **different failure mode**, but both show **operational risk** when AI touches production paths.

[Java4Shell](https://explainx.ai/blog/java4shell-gpt-6-cyber-cve-2026-114938-oracle-patch-november-2026) demonstrated **AI finding RCE**; this week demonstrates **AI causing credential exposure**. Security programs need **both** vulnerability review and **agent governance**.

## What Together AI does not claim

The post does **not** say every Together customer was affected. It does **not** name the intruder. It does **not** publish counts of prompts or customers in the Hugging Face archive. It does **not** assert HIPAA or GDPR conclusions; **review is ongoing**.

Treat **"data deleted"** as **Together AI's understanding**, not independently verified in the notice itself.

## Compliance checklist for security teams

Security reviewers can work through this list without waiting for a personalized email:

1. **Inventory** which products called Together**serverless** (not dedicated endpoints) in**June–July 2026** .
2. **Filter** logs for**MiniMax M3** ,**GLM-5.2** , and**Kimi K2.6** model strings on the four named dates.
3. **Classify** whether prompts could contain**regulated data** ,**source code** , or**live credentials** .
4. **Enable ZDR** on active workspaces and document the toggle date.
5. **Open a ticket** with**[security@together.ai](mailto:security@together.ai)** if regulated data might be in scope.
6. **Rotate** any API keys, OAuth tokens, or database passwords that ever appeared inside prompts.
7. **Review xorl forks** if your org contributed patches; ensure you never committed**HF or cloud tokens** .

Pair this with internal **canary-token** drills modeled on Dragos's public methodology. You do not need two million prompts; a **dozen unique canaries** per environment is enough to catch **unexpected log sinks**.

## Why AI coding agents multiply secret risk

Coding agents autocomplete **environment files**, **CI configs**, and **integration tests**. A single bad suggestion that lands on `main` can expose **months of customer prompts** stored elsewhere.

Mitigations that match Together AI's post-incident list:

| Control | What it blocks | 
|---|---|
| Short-lived HF tokens | Stolen creds expire before archive download | 
| PR secret scanning | Agents cannot merge keys into xorl-like repos | 
| Separate synthetic eval data | HF test repos hold fake prompts only | 
| Human review on credential paths | Agents never touch secret stores unsupervised | 

If your workshop team is rolling out **Claude Code** or **Codex** broadly, pair tool training with **secret hygiene**, not just prompt craft. explainx.ai covers live formats in [Claude workshop guidance](https://explainx.ai/blog/what-is-claude-ai-workshop-formats-pricing-how-to-choose-2026).

## Related reading

Sources: [Together AI security notice](https://www.together.ai/blog/security-event-prompt-leakage-for-requests-in-june-and-july-of-2026?ref=explainx) (November 21, 2026), [Dragos canary post](https://www.dragos.com/blog/ai-supply-chain-security-canary-tokens?ref=explainx) (November 19, 2026).
